fix: drift-scanner pods cleanup script and guide

- add cleanup script for failed drift-scanner pods
- add comprehensive fix guide with prevention strategies
- resolve pod resource issues in K8s cluster

DRIFT_SCANNER_FIX_GUIDE.md

@@ -0,0 +1,159 @@
+# Drift Scanner Pods  Fix Guide
+
+## Problem Analysis
+You have multiple drift-scanner pods that are failing or completed:
+- 6 Failed pods: drift-scanner-29602260-sns8t, drift-scanner-29602320-vf6dj, etc.
+- 3 Succeeded pods: drift-scanner-29613600-x67jn, etc.
+
+## Root Cause
+These drift-scanner pods appear to be external Kubernetes Jobs (not part of your codebase) that are created by an external system or cron job. The numeric suffixes suggest time-based job scheduling.
+
+## Immediate Fix Actions
+
+### Option 1: Manual Cleanup (Quick Fix)
+```bash
+# SSH to your K8s server
+ssh wooo@192.168.0.110
+
+# Delete failed pods
+sudo kubectl delete pod drift-scanner-29602260-sns8t -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29602320-vf6dj -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29602380-862vh -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29602440-mwd7m -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29602500-gpr27 -n momo --force --grace-period=0
+
+# Delete old succeeded pods (optional)
+sudo kubectl delete pod drift-scanner-29613600-x67jn -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29613660-7tk4d -n momo --force --grace-period=0
+sudo kubectl delete pod drift-scanner-29613720-c7zcp -n momo --force --grace-period=0
+```
+
+### Option 2: Use Cleanup Script
+```bash
+# On K8s server
+cd /home/wooo/scripts
+./cleanup_drift_scanner_pods.sh cleanup-failed
+```
+
+### Option 3: Batch Cleanup
+```bash
+# Delete all drift-scanner pods at once
+sudo kubectl delete pods -l app=drift-scanner -n momo --force --grace-period=0
+```
+
+## Prevention Strategies
+
+### 1. Identify the Source
+Find what's creating these drift-scanner jobs:
+```bash
+# Check for CronJobs
+sudo kubectl get cronjobs -n momo
+sudo kubectl get cronjobs --all-namespaces | grep drift
+
+# Check for scheduled jobs
+sudo kubectl get jobs -n momo | grep drift
+sudo kubectl get jobs --all-namespaces | grep drift
+
+# Check events
+sudo kubectl get events -n momo --sort-by='.lastTimestamp' | grep drift
+```
+
+### 2. Monitor and Auto-Cleanup
+Add to your existing health monitoring script (`/home/wooo/scripts/k8s_health_monitor.sh`):
+
+```bash
+# Add this function to the script
+check_drift_scanner_pods() {
+    local drift_pods=$(sudo kubectl get pods -n ${MOMO_NAMESPACE} --no-headers | grep drift-scanner || echo "")
+    
+    if [[ -n "$drift_pods" ]]; then
+        local failed_count=$(echo "$drift_pods" | grep "Failed" | wc -l)
+        local succeeded_count=$(echo "$drift_pods" | grep "Succeeded" | wc -l)
+        
+        if [[ $failed_count -gt 5 ]] || [[ $succeeded_count -gt 10 ]]; then
+            log "WARNING: Too many drift-scanner pods (Failed: $failed_count, Succeeded: $succeeded_count)"
+            
+            # Auto-cleanup failed pods
+            echo "$drift_pods" | grep "Failed" | awk '{print $1}' | xargs -r sudo kubectl delete pod -n ${MOMO_NAMESPACE} --force --grace-period=0
+            
+            # Auto-cleanup old succeeded pods (older than 24h)
+            echo "$drift_pods" | grep "Succeeded" | awk '{print $1}' | xargs -r sudo kubectl delete pod -n ${MOMO_NAMESPACE} --force --grace-period=0
+        fi
+    fi
+}
+```
+
+### 3. Resource Limits
+If these are legitimate jobs, consider setting resource limits and TTL:
+```yaml
+# Example Job template with TTL
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: drift-scanner
+spec:
+  ttlSecondsAfterFinished: 3600  # Clean up after 1 hour
+  backoffLimit: 3               # Limit retries
+  template:
+    spec:
+      containers:
+      - name: drift-scanner
+        image: your-image
+        resources:
+          requests:
+            memory: "128Mi"
+            cpu: "100m"
+          limits:
+            memory: "512Mi"
+            cpu: "500m"
+      restartPolicy: OnFailure
+```
+
+## Monitoring Setup
+
+### Add to Prometheus Monitoring
+Create alert rule in `/home/wooo/monitoring/prometheus.yml`:
+
+```yaml
+- alert: TooManyFailedDriftScannerPods
+  expr: kube_pod_status_phase{phase="Failed", pod=~"drift-scanner-.*"} > 5
+  for: 5m
+  labels:
+    severity: warning
+  annotations:
+    summary: "Too many failed drift-scanner pods"
+    description: "More than 5 drift-scanner pods have failed"
+```
+
+### Telegram Alert Integration
+The cleanup script already includes Telegram notifications when pods are cleaned up.
+
+## Long-term Solutions
+
+1. **Identify the Owner**: Find which system or team is creating these drift-scanner jobs
+2. **Fix the Root Cause**: Address why these jobs are failing
+3. **Implement TTL**: Add `ttlSecondsAfterFinished` to job specifications
+4. **Resource Quotas**: Set limits to prevent resource exhaustion
+5. **Regular Cleanup**: Schedule the cleanup script to run periodically
+
+## Emergency Commands
+```bash
+# Quick check of drift-scanner status
+sudo kubectl get pods -n momo | grep drift-scanner
+
+# Force delete all drift-scanner pods
+sudo kubectl delete pods -n momo --all --force --grace-period=0 --selector=app=drift-scanner
+
+# Check what's creating them
+sudo kubectl get events -n momo --sort-by='.lastTimestamp' | tail -20
+```
+
+## Files Created
+- `scripts/cleanup_drift_scanner_pods.sh` - Comprehensive cleanup script
+- `DRIFT_SCANNER_FIX_GUIDE.md` - This guide
+
+## Next Steps
+1. Run the immediate cleanup commands
+2. Identify the source of drift-scanner jobs
+3. Implement prevention measures
+4. Set up monitoring and auto-cleanup

scripts/cleanup_drift_scanner_pods.sh

@@ -0,0 +1,215 @@
+#!/bin/bash
+# Drift Scanner Pods Cleanup Script
+#  cleans up failed drift-scanner pods and provides analysis
+
+set -e
+
+# Configuration
+NAMESPACE="momo"
+LOG_FILE="/var/log/drift_scanner_cleanup.log"
+TELEGRAM_BOT_TOKEN="8075645931:AAH-EGKMo8ZC4QJs-Nc1_0s92xHrGdQvdpg"
+TELEGRAM_CHAT_ID="5619078117"
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+# Logging function
+log() {
+    echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" | tee -a "$LOG_FILE"
+}
+
+# Telegram notification
+send_telegram() {
+    local message="$1"
+    curl -s -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
+        -d chat_id="${TELEGRAM_CHAT_ID}" \
+        -d text="${message}" \
+        -d parse_mode="HTML" > /dev/null 2>&1
+}
+
+# Check kubectl access
+check_kubectl() {
+    if ! kubectl get pods -n "$NAMESPACE" > /dev/null 2>&1; then
+        log "${RED}ERROR: kubectl access denied or namespace not found${NC}"
+        exit 1
+    fi
+}
+
+# Get drift-scanner pods status
+get_drift_scanner_pods() {
+    kubectl get pods -n "$NAMESPACE" --no-headers | grep drift-scanner || echo ""
+}
+
+# Analyze pod status
+analyze_pods() {
+    log "${YELLOW}=== Drift Scanner Pod Analysis ===${NC}"
+    
+    local pods=$(get_drift_scanner_pods)
+    if [[ -z "$pods" ]]; then
+        log "${GREEN}No drift-scanner pods found${NC}"
+        return 0
+    fi
+    
+    local total=0
+    local failed=0
+    local succeeded=0
+    local running=0
+    
+    while read -r pod_name ready status restarts age; do
+        [[ -z "$pod_name" ]] && continue
+        ((total++))
+        
+        case "$status" in
+            "Failed")
+                ((failed++))
+                log "${RED}FAILED: $pod_name (Ready: $ready, Restarts: $restarts, Age: $age)${NC}"
+                ;;
+            "Succeeded")
+                ((succeeded++))
+                log "${GREEN}SUCCEEDED: $pod_name (Ready: $ready, Restarts: $restarts, Age: $age)${NC}"
+                ;;
+            "Running")
+                ((running++))
+                log "${YELLOW}RUNNING: $pod_name (Ready: $ready, Restarts: $restarts, Age: $age)${NC}"
+                ;;
+            *)
+                log "${YELLOW}UNKNOWN: $pod_name (Status: $status, Ready: $ready, Restarts: $restarts, Age: $age)${NC}"
+                ;;
+        esac
+    done <<< "$pods"
+    
+    log "${YELLOW}Summary: Total=$total, Failed=$failed, Succeeded=$succeeded, Running=$running${NC}"
+    
+    # Return counts for use in other functions
+    echo "$total|$failed|$succeeded|$running"
+}
+
+# Clean up failed pods
+cleanup_failed_pods() {
+    log "${YELLOW}=== Cleaning Up Failed Pods ===${NC}"
+    
+    local failed_pods=$(kubectl get pods -n "$NAMESPACE" --no-headers | grep drift-scanner | grep "Failed" | awk '{print $1}')
+    
+    if [[ -z "$failed_pods" ]]; then
+        log "${GREEN}No failed drift-scanner pods to clean${NC}"
+        return 0
+    fi
+    
+    local cleaned_count=0
+    while read -r pod_name; do
+        [[ -z "$pod_name" ]] && continue
+        
+        log "Deleting failed pod: $pod_name"
+        if kubectl delete pod "$pod_name" -n "$NAMESPACE" --force --grace-period=0; then
+            ((cleaned_count++))
+            log "${GREEN}Successfully deleted: $pod_name${NC}"
+        else
+            log "${RED}Failed to delete: $pod_name${NC}"
+        fi
+    done <<< "$failed_pods"
+    
+    log "${GREEN}Cleaned up $cleaned_count failed pods${NC}"
+    return $cleaned_count
+}
+
+# Clean up succeeded pods (optional, based on age)
+cleanup_succeeded_pods() {
+    local max_age_hours="${1:-24}"  # Default 24 hours
+    
+    log "${YELLOW}=== Cleaning Up Succeeded Pods (older than ${max_age_hours}h) ===${NC}"
+    
+    local succeeded_pods=$(kubectl get pods -n "$NAMESPACE" --no-headers | grep drift-scanner | grep "Succeeded")
+    
+    if [[ -z "$succeeded_pods" ]]; then
+        log "${GREEN}No succeeded drift-scanner pods to clean${NC}"
+        return 0
+    fi
+    
+    local cleaned_count=0
+    while read -r pod_name ready status restarts age; do
+        [[ -z "$pod_name" ]] && continue
+        
+        # Convert age to hours (simplified - handles Xh, Xd, XhXm formats)
+        local age_hours=0
+        if [[ "$age" =~ ^([0-9]+)h$ ]]; then
+            age_hours=${BASH_REMATCH[1]}
+        elif [[ "$age" =~ ^([0-9]+)d$ ]]; then
+            age_hours=$((${BASH_REMATCH[1]} * 24))
+        elif [[ "$age" =~ ^([0-9]+)h([0-9]+)m$ ]]; then
+            age_hours=${BASH_REMATCH[1]}
+        fi
+        
+        if [[ $age_hours -gt $max_age_hours ]]; then
+            log "Deleting old succeeded pod: $pod_name (Age: $age)"
+            if kubectl delete pod "$pod_name" -n "$NAMESPACE" --force --grace-period=0; then
+                ((cleaned_count++))
+                log "${GREEN}Successfully deleted: $pod_name${NC}"
+            else
+                log "${RED}Failed to delete: $pod_name${NC}"
+            fi
+        fi
+    done <<< "$succeeded_pods"
+    
+    log "${GREEN}Cleaned up $cleaned_count old succeeded pods${NC}"
+    return $cleaned_count
+}
+
+# Main function
+main() {
+    local action="${1:-analyze}"
+    local max_age="${2:-24}"
+    
+    log "${YELLOW}=== Drift Scanner Pod Cleanup Script ===${NC}"
+    log "Action: $action"
+    log "Namespace: $NAMESPACE"
+    
+    # Check kubectl access
+    check_kubectl
+    
+    # Analyze current state
+    local analysis=$(analyze_pods)
+    local total=$(echo "$analysis" | cut -d'|' -f1)
+    local failed=$(echo "$analysis" | cut -d'|' -f2)
+    local succeeded=$(echo "$analysis" | cut -d'|' -f3)
+    local running=$(echo "$analysis" | cut -d'|' -f4)
+    
+    case "$action" in
+        "analyze")
+            log "${GREEN}Analysis complete. No cleanup performed.${NC}"
+            ;;
+        "cleanup-failed")
+            cleanup_failed_pods
+            local cleaned_failed=$?
+            if [[ $cleaned_failed -gt 0 ]]; then
+                send_telegram "Cleaned up $cleaned_failed failed drift-scanner pods"
+            fi
+            ;;
+        "cleanup-succeeded")
+            cleanup_succeeded_pods "$max_age"
+            local cleaned_succeeded=$?
+            if [[ $cleaned_succeeded -gt 0 ]]; then
+                send_telegram "Cleaned up $cleaned_succeeded old succeeded drift-scanner pods"
+            fi
+            ;;
+        "cleanup-all")
+            cleanup_failed_pods
+            cleanup_succeeded_pods "$max_age"
+            ;;
+        *)
+            echo "Usage: $0 [analyze|cleanup-failed|cleanup-succeeded|cleanup-all] [max-age-hours]"
+            echo "  analyze         - Show current pod status (default)"
+            echo "  cleanup-failed  - Delete all failed pods"
+            echo "  cleanup-succeeded - Delete succeeded pods older than max-age-hours (default: 24h)"
+            echo "  cleanup-all     - Delete failed pods and old succeeded pods"
+            exit 1
+            ;;
+    esac
+    
+    log "${GREEN}=== Script completed ===${NC}"
+}
+
+# Run main function with all arguments
+main "$@"